Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “interpretability”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

The impact of non-uniform thermal structure on the interpretation of exoplanet emission spectra

The determination of atmospheric structure and molecular abundances of planetary atmospheres via spectroscopy involves direct comparisons between models and data. While varying in sophistication, most model spectra comparisons fundamentally assume one-dimensional (1D) model physics. However, knowledge from general circulation models and of solar system planets suggests that planetary atmospheres are inherently three-dimensional in their structure and composition. We explore the potential biases resulting from standard “1D” assumptions within a Bayesian atmospheric retrieval framework. Specifically, we show how the assumption of a single 1D thermal profile can bias our interpretation of the thermal emission spectrum of a hot Jupiter atmosphere that is composed of two thermal profiles. We retrieve spectra of unresolved model planets as observed with a combination of the Hubble Space Telescope Wide Field Camera 3 (WFC3)+Spitzer Infrared Array Camera (IRAC) as well as the James Webb Space Telescope (JWST) under varying differences in the two thermal profiles. For WFC3+IRAC, there is a significantly biased estimate of CH{sub 4} abundance using a 1D model when the contrast is 80%. For JWST, two thermal profiles are required to adequately interpret the data and estimate the abundances when contrast is greater than 40%. We also apply this preliminary concept to the recent WFC3+IRAC phase curve data of the hot Jupiter WASP-43b. We see similar behavior as present in our simulated data: while the H{sub 2}O abundance determination is robust, CH{sub 4} is artificially well-constrained to incorrect values under the 1D assumption. Our work demonstrates the need to evaluate model assumptions in order to extract meaningful constraints from atmospheric spectra and motivates exploration of optimal observational setups.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2017

Transient Cosmic-ray Events beyond the Heliopause: Interpreting Voyager-1 Observations

In 2013 March and 2014 May, Voyager-1 ( V1 ) experienced small but significant increases in the flux of galactic cosmic rays (GCRs) in the hundred MeV/n range. Additionally, V1 also saw episodic depletion of GCR flux around perpendicular pitch angles. We discuss the pitch-angle distribution and the time profiles of these events. In a previous paper, we interpreted the 2013 “bump” as the GCRs remotely sensing a shock that reached the magnetic field line passing through V1 : particles gained energy as they were reflected on the approaching region of the stronger magnetic field of the disturbance. Here, we point out that energy gain is not restricted to reflected particles—GCRs passing through the disturbance also gain energy. The effect should be present in a broad range of pitch angles with the maximum increase of GCR intensity predicted to occur at the critical reflection angle. In this paper, the shock is not step-like, but a gradual increase of the magnetic field strength, B , taking a few days, in agreement with V1 measurements. This smoothens the profile of the predicted bump in the GCR flux. We also address the linear episodic decreases seen around perpendicular pitch angles. These events are interpreted in terms of adiabatic cooling behind the shock due to the slow weakening of B . We present simple numerical model calculations and find that a gradual shock followed by a slow decrease of B , as observed, may account for both the episodic increases and the anisotropic depletion of GCR fluxes.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Effects of Subhalos on Interpreting Highly Magnified Sources Near Lensing Caustics

Large magnification factors near gravitational lensing caustics of galaxy-cluster lenses allow the study of individual stars or compact stellar associations at cosmological distances. We study how the presence of sub-galactic subhalos, an inevitable consequence of cold dark matter, can alter the property of caustics and hence change the interpretation of highly magnified sources that lie atop them. First, we consider a galaxy-cluster halo populated with subhalos sampled from a realistic subhalo mass function calibrated to N-body simulations. Then, we compare a semianalytical approximation and an adaptive ray-shooting method that we employ to quantify the property of the caustics. As a case study, we investigate Earendel, a z = 6.2 candidate of magnified single- or multiple-star system with a lone lensed image atop the critical curve in the Sunrise Arc. We find that the source size constraint (≲0.3 pc) previously derived from macrolens models should be relaxed by a factor of a few to 10 when subhalos are accounted for, therefore allowing the possibility of a compact star cluster. The subhalos could introduce an astrometric perturbation that is ≲0$^{"}_{.}$5, which does not contradict observation. These conclusions are largely robust to changes in the subhalo population. Subhalos therefore should be seriously accounted for when interpreting the astrophysical nature of similar highly magnified sources uncovered in recent high-z observations.

Caustic curve↗
DOE OSTI2016

Interpreting space-based trends in carbon monoxide with multiple models

Here, we use a series of chemical transport model and chemistry climate model simulations to investigate the observed negative trends in MOPITT CO over several regions of the world, and to examine the consistency of time-dependent emission inventories with observations. We also found that simulations driven by the MACCity inventory, used for the Chemistry Climate Modeling Initiative (CCMI), reproduce the negative trends in the CO column observed by MOPITT for 2000–2010 over the eastern United States and Europe. However, the simulations have positive trends over eastern China, in contrast to the negative trends observed by MOPITT. The model bias in CO, after applying MOPITT averaging kernels, contributes to the model–observation discrepancy in the trend over eastern China. This demonstrates that biases in a model's average concentrations can influence the interpretation of the temporal trend compared to satellite observations. The total ozone column plays a role in determining the simulated tropospheric CO trends. A large positive anomaly in the simulated total ozone column in 2010 leads to a negative anomaly in OH and hence a positive anomaly in CO, contributing to the positive trend in simulated CO. Our results demonstrate that accurately simulating variability in the ozone column is important for simulating and interpreting trends in CO.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

AttentionFire_v1.0: interpretable machine learning fire model for burned-area predictions over tropics

Abstract. African and South American (ASA) wildfires account for more than 70 % of global burned areas and have strong connection to local climate for sub-seasonal to seasonal wildfire dynamics. However, representation of the wildfire–climate relationship remains challenging due to spatiotemporally heterogenous responses of wildfires to climate variability and human influences. Here, we developed an interpretable machine learning (ML) fire model (AttentionFire_v1.0) to resolve the complex controls of climate and human activities on burned areas and to better predict burned areas over ASA regions. Our ML fire model substantially improved predictability of burned areas for both spatial and temporal dynamics compared with five commonly used machine learning models. More importantly, the model revealed strong time-lagged control from climate wetness on the burned areas. The model also predicted that, under a high-emission future climate scenario, the recently observed declines in burned area will reverse in South America in the near future due to climate changes. Our study provides a reliable and interpretable fire model and highlights the importance of lagged wildfire–climate relationships in historical and future predictions.

58 GEOSCIENCES↗
DOE OSTI2018

Evolution, Current State of the Art, and Interpretation of Aircraft-Based Methane Emission Quantification at the Natural Gas Basin-Level

Accurately quantifying methane (CH4) emissions from the oil and gas (O&G) industry is challenging given the existence of many potential emission sources, differences in industry practices and regulations, and often incomplete or out-of-date activity data. It is thus important to regularly assess emission inventories and support improvements by deriving independent estimates using state-of-the-science approaches. Recent research has provided CH4 emission estimates from the O&G supply chains based on different measurement techniques at multiple spatio-temporal scales. Natural gas basin-scale aircraft-based atmospheric measurements indicate greater CH4 emissions than emission inventories based on up-scaling of component-/facility-level emission measurements from a relatively small sample size. Here we present results from a coordinated field study that compares concurrent CH4 emission measurements using different techniques and scales to better understand the strengths and weaknesses of each approach, with a focus on the aircraft-based estimation method. We describe the importance of (i) decades of measurement technology development, (ii) experience in designing measurement sampling strategies and aligning system boundaries, and (Hi) properly interpreting CH4 emission estimates for successfully reconciling aircraft-based measurements with emission inventories and for identifying CH4 emission mitigation potential. We illustrate that aircraft-based top-down estimates represent a brief snapshot of total basin-level CH4 emissions. Thus, a high spatio-temporally resolved bottom-up emission inventory is needed to identify key CH4 sources (including episodic sources) at the process level. While this paper provides a brief overview of the overall study design and findings, its focus is on the implementation of the aircraft measurements and its interpretation and results. A separate paper describes in more detail the overall organizational structure of the study as well as the study implications from an industry perspective.

03 NATURAL GAS↗
DOE OSTI2023

An Interpretable Index of Social Vulnerability to Environmental Hazards

Index-based measures of social vulnerability to environmental hazards are commonly modeled from composites of population-level risk factors. These models overlook individual context in communities' experiences of environmental hazards, producing metrics that may hinder spatial decision support for mitigating and responding to hazards. This paper introduces an interpretable, high-resolution model for generating an individual-oriented social vulnerability index (IOSVI) for the United States built on synthetic populations that couples individual and social determinants of vulnerability. The IOSVI combines an individual vulnerability index (IVI) that ranks individuals in an area’s synthetic population based on intersecting risk factors, with a social vulnerability index (SVI) based on the population’s cumulative distribution of IVI scores. Interpretability of the IOSVI procedure is demonstrated through examples of national, metropolitan, and neighborhood (census tract) level spatial variation in index scores and IVI themes, as well as an exploratory analysis examining risk factors affecting a specific sub-population (military veterans) in areas of high social and environmental vulnerability.

Tuccillo, Joe↗
DOE OSTI2013

Back from the Brink with Something for Everyone - The Final Executed Memorandum of Agreement for Interpretation of the East Tennessee Technology Park and the K-25 Building - 13370

When the Environmental Management (EM) Program at the Oak Ridge Office of the Department of Energy (DOE) began its major decontamination and decommissioning (D and D) program activities in the mid-1990's, it was understood that the work to demolish the gaseous diffusion process buildings at the K-25 Site, as it was then known, would be challenging. Nothing of that size and breadth had ever been done within the DOE complex and the job brought about a full menu of unique attributes: radiological contamination with enriched materials entrained in certain areas of the system, a facility that was never designed not to operate but had been shut down since 1964, and a loyal following of individuals and organizations who were committed to the physical preservation of at least some portion of the historic Manhattan Project property. DOE was able to solve and resolve the issues related to nuclear materials management, contamination control, and determining the best way to safely and efficiently deconstruct the massive building. However, for a variety of reasons, resolution of the historic preservation questions - what and how much to preserve, how to preserve it, where to preserve it, how to interpret it, how much to spend on preservation, and by and for whom preservation should occur - remained open to debate for over a decade. After a dozen years, countless meetings, phone calls, discussions and other exchanges, and four National Historic Preservation Act (NHPA) [1] Memoranda of Agreement (MOA), a final MOA [2] has been executed. The final executed MOA's measures are robust, creative, substantive, and will be effective. They include a multi-story replica of a portion of the K-25 Building, the dedication of the K-25 Building footprint for preservation purposes, an equipment building to house authentic Manhattan Project and Cold War equipment, a virtual museum, an on-site history center, a grant to preserve a historically-significant Manhattan Project-era hotel in Oak Ridge, and more. The MOA was designed to offer something for everyone. The MOA for the K- 25 Building and interpretation of the East Tennessee Technology Park (ETTP; formerly the K-25 Site) was executed by all of the signatory parties on August 7, 2012 - almost 67 years to-the-day after the 'product' of the K-25 process building became known to more than just a small group of scientists and engineers working on a secret project for the Army Corps of Engineers Manhattan District. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

MicroBooNE investigations on the photon interpretation of the MiniBooNE low energy excess

The MicroBooNE experiment is a liquid argon time projection chamber with 85-ton active volume at Fermilab, operated from 2015 to 2020 to collect neutrino data from Fermilab's Booster Neutrino Beam. One of MicroBooNE's physics goals is to investigate possible explanations of the low-energy excess observed by the MiniBooNE experiment in $\nu_{\mu}\rightarrow \nu_{e}$ neutrino oscillation measurements. MicroBooNE has performed searches to test hypothetical interpretations of the MiniBooNE low-energy excess, including the underestimation of the photon background or instrinic $\nu_{e}$ background. This thesis presents MicroBooNE's searches for two neutral current (NC) single-photon production processes that contribute to the photon background of the MiniBooNE measurement: NC $\Delta$ resonance production followed by $\Delta$ radiative decay: $\Delta \rightarrow N\gamma$, and NC coherent single-photon production. Both searches take advantage of boosted decision trees to yield efficient background rejection, and a high-statistic NC $\pi^0$ measurement to constrain dominant background, and make use of MicroBooNE's first three years of data. The NC $\Delta \rightarrow N\gamma$ measurement yielded a bound on the $\Delta$ radiative decay process at 2.3 times the predicted nominal rate at 90\% confidence level(C.L.), disfavoring a candidate photon interpretation of the MiniBooNE low-energy excess as a factor of 3.18 times the nominal NC Δ radiative decay rate at the 94.8\% C.L. The NC coherent single photon measurement leads to the world's first experimental limit on the cross-section of this process below 1 GeV, of $1.49 \times 10^{-41} \text{cm}^2$ at 90\% C.L., corresponding to 24.0 times the nominal prediction.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Nonparametric Multiparticle Set Methods for Interpreting Environmental Samples

Collection and analysis of environmental samples is commonly used by a range of stakeholders in nuclear safeguards and security contexts. While the ubiquity of samples and their transport in the environment allow regular collection, developing and demonstrating methods for analyzing these samples is difficult. In this work, an environmental sample consists of a set of one or more individual particles. Recent advances in reactor simulation have allowed us to generate data that are more representative of real-world environmental samples, enabling statistically defensible method development and testing. The most notable of these advances is a drastic increase in the number of material depletion regions, which allows our simulations to capture the variation in isotopic composition seen at length scales consistent with environmental samples. Traditional approaches for handling multiparticle samples treat each particle in the sample individually, estimating the quantity of interest (e.g., core-average burnup) resulting from measurement and analysis of signatures (e.g., nuclide assays) from each individual particle. Individual estimates are then averaged to generate a single estimate of the quantity of interest over the entire sample. In this presentation, we introduce two novel approaches for interpreting environmental samples that comprise of multiple particles: (1) the Quantile-Quantile Comparator, which uses a multivariate generalization of quantile-quantile plots for comparing unknown statistical distributions, and (2) the Set Transformer, an attention-based neural network module designed to model interactions among elements (particles) in the input set (sample). Statistically representative sampling cannot be guaranteed as samples are passively collected and are beholden to what particles are available in the environment. These new analysis methods for set-input problems are expected to be more robust than traditional approaches to issues of sampling bias where particles are not uniformly distributed throughout regions of interest, as well as generally outperform traditional approaches by jointly considering all elements in the set. We will present results comparing the performance of traditional single particle approaches and the novel Quantile-Quantile Comparator and Set Transformer for interpretation of simulated environmental samples.

Phathanapirom, Birdy↗
DOE OSTI2025

A multiscale design method using interpretable machine learning for phononic materials with closely interacting scales

Manipulating the dispersive characteristics of vibrational waves is beneficial for many applications, e.g., high-precision instruments. architected hierarchical phononic materials have sparked promise tunability of elastodynamic waves and vibrations over multiple frequency ranges. In this article, hierarchical unit-cells are obtained, where features at each length scale result in a band gap within a targeted frequency range. Our novel approach, the ‘‘hierarchical unit-cell template method,’’ is an interpretable machine-learning approach that uncovers global unit-cell shape/topology patterns corresponding to predefined band-gap objectives. A scale-separation effect is observed where the coarse-scale band-gap objective is mostly unaffected by the fine-scale features despite the closeness of their length scales, thus enabling an efficient hierarchical algorithm. Moreover, the hierarchical patterns revealed are not predefined or self-similar hierarchies as common in current hierarchical phononic materials. Furthermore, our approach offers a flexible and efficient method for the exploration of new regions in the hierarchical design space, extracting minimal effective patterns for inverse design in applications targeting multiple frequency ranges.

Architected materials↗
DOE OSTI2025

TRANSP integrated modeling code for interpretive and predictive analysis of tokamak plasmas

This paper provides a comprehensive review of the TRANSP code, a sophisticated tool for interpretive and predictive analysis of tokamak plasmas, detailing its major capabilities and features. It describes the equations for particle, power, and momentum balance analysis, as well as the poloidal field diffusion equations. The paper outlines the spatial and time grids used in TRANSP and details the equilibrium assumptions and solvers. Various models for heating and current drive and radiation, including updates to the NUBEAM model, are discussed. The handling of large-scale events such as sawtooth crashes and pellet injections is examined, along with the predictive capabilities for advancing plasma profiles. The integration of TRANSP with the ITER Integrated Modeling and Analysis Suite (IMAS) is highlighted, demonstrating enhanced data access and analysis capabilities. Additionally, the paper discusses best practices and continuous integration techniques to enhance TRANSP's robustness. The suite of TRANSP tools, designed for efficient data analysis and simulation, further supports the optimization of tokamak operations and coupling with other tokamak codes. Continuous development and support ensure that TRANSP remains a major code for the analysis of experimental data for controlled thermonuclear fusion, maintaining its critical role in supporting the optimization of tokamak operations and advancing fusion research.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

How to see hidden patterns in metamaterials with interpretable machine learning

Machine learning models can assist with metamaterials design by approximating computationally expensive simulators or solving inverse design problems. However, past work has usually relied on black box deep neural networks, whose reasoning processes are opaque and require enormous datasets that are expensive to obtain. Here, in this work, we develop two novel machine learning approaches to metamaterials discovery that have neither of these disadvantages. These approaches, called shape-frequency features and unit-cell templates, can discover 2D metamaterials with user-specified frequency band gaps. Our approaches provide logical rule-based conditions on metamaterial unit-cells that allow for interpretable reasoning processes, and generalize well across design spaces of different resolutions. The templates also provide design flexibility where users can almost freely design the fine resolution features of a unit-cell without affecting the user’s desired band gap.

36 MATERIALS SCIENCE↗
DOE OSTI2026

End-To-End Decentralized Transmission Line Protection in IBR-Dominated Weak Grids Using Interpretable Data-Driven Methods

Traditional transmission line protection relies on predictable synchronous-based fault signatures, which frequently fail under the non-standard, current-limited fault characteristics of Inverter-Based Resources (IBRs). This study investigates how to achieve secure, communication-free fault isolation in IBR-dominated weak grids without relying on opaque, computationally heavy "black-box" machine learning algorithms. To address this, we propose a novel, standalone, and inherently interpretable data-driven protection framework. Unlike centralized methods requiring multi-terminal communication, this decentralized approach relies solely on local measurements using a hierarchical linear-kernel Support Vector Machine (SVM). The methodology decomposes the protection task into four sequential stages that mimic traditional protection elements: fault detection and fault direction identification, fault type classification, zone classification, and location estimation. This multi-stage architecture allows for specialized feature engineering at each stage, combining high computational efficiency with logic traceability. The framework's end-to-end performance was validated via C-code and PSCAD/EMTDC co-simulation, utilizing a real-world utility network and an OEM black-box IBR model. The proposed relay achieves 97.2% overall accuracy and provides a reliable trip decision within a 2.5-cycle window. The results confirm 100% accuracy in fundamental fault detection, reliable zone selectivity across low to moderate fault resistances, and robust security against non-fault transients, proving its immediate viability for integration into commercial numerical relays.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2018

Above zone pressure interpretation for leaky well characterization and its identification from leaky caprock/fault

Pressure transient analysis has long been used for reservoir characterization. Above-zone (AZ) pressure has been recently investigated for inferring leakage pathway characteristics in leakage events from subsurface injection operations. The recorded pressure in the AZ should be purely related to leakage and therefore it can be safely inverted to deduce leakage characteristics. It is crucial to evaluate fluid leakage through abandoned wells to plan for further measurements of leakage prevention. However, the recorded AZ leakage signal may not be related to leaky well(s). Therefore, identification and spatial investigation of well leakage is required for leakage evaluation. Here in this paper, we propose a pressure interpretation method for early detection of leaky pathways, applying two observation points in the AZ. We distinguish leaky well, fault and caprock based on their corresponding flow regime identification. We show that the pressure difference of the two observation wells can be applied as a proxy for unknown leakage rate, which is crucial for leakage identification as well as characterization. Results show that the estimated location of the leaky well, leakage coefficient, and the leakage rate are in good agreement with the actual values. The estimated leakage coefficient of the leaky well can be used to evaluate well leakage in multiphase systems such as carbon dioxide leakage in deep saline aquifers.

02 PETROLEUM↗
DOE OSTI2019

Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks

X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials. We propose a machine-learning-enabled approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD patterns. We overcome the scarce-data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data. As a test case, 115 thin-film metal-halides spanning 3 dimensionalities and 7 space-groups are synthesized and classified. After testing various algorithms, we develop and implement an all convolutional neural network, with cross-validated accuracies for dimensionality and space-group classification of 93% and 89%, respectively. We propose average class activation maps, computed from a global average pooling layer, to allow high model interpretability by human experimentalists, elucidating the root-causes of misclassification. Finally, we systematically evaluate the maximum XRD pattern step size (data acquisition rate) before loss of predictive accuracy occurs, and determine it to be 0.16° 2θ, which enables an XRD pattern to be obtained and classified in 5.5 minutes or less.

36 MATERIALS SCIENCE↗
DOE OSTI2023

End-to-end AI framework for interpretable prediction of molecular and crystal properties

We introduce an end-to-end computational framework that allows for hyperparameter optimization using the DeepHyper library, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-NET. We employ these AI models along with the benchmark QM9, hMOF, and MD17 datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Interpretable Data-Driven Probabilistic Power System Load Margin Assessment with Uncertain Renewable Energy and Loads

The increasing uncertainties caused by the high-penetration of stochastic renewable generation resources poses a significant threat to the power system voltage stability. To address this issue, this paper proposes a probabilistic deep kernel learning enabled surrogate model to extract the hidden relationship between uncertain sources, i.e., wind power and loads, and load margin for probabilistic load margin assessment (PLMA). Unlike other deep learning approaches, a kernel SHAP provides the sensitivity analysis as well as interpretability of the inputs to outputs influences. This allows identifying the critical factors that affect load margin so that corrective control can be initiated for stability enhancement. Numerical results carried out on the IEEE 118-bus power system demonstrate the accuracy and efficiency of the proposed data-driven PLMA scheme.

deep kernel learning↗